Supplemental Material for Face Alignment Across Large Poses: A 3D Solution
|
|
- Stewart Pearson
- 5 years ago
- Views:
Transcription
1 Supplemental Material for Face Alignment Across Large Poses: A 3D Solution Xiangyu Zhu 1 Zhen Lei 1 Xiaoming Liu 2 Hailin Shi 1 Stan Z. Li 1 1 Institute of Automation, Chinese Academy of Sciences 2 Department of Computer Science and Engineering, Michigan State University {xiangyu.zhu,zlei,hailin.shi,szli}@nlpr.ia.ac.cn liuxm@msu.edu 1. Results Demo In this section, we demonstrate some alignment results of 3DDFA in AFLW in Fig. 1. Since the landmark visibility can be easily computed from the fitted dense 3D model [1], we also demonstrate the landmark visibility. Figure 1. The results of 3DDFA in AFLW. For each pair, the left one renders the fitted 3D shape with the mean texture, which is made transparent to demonstrate the fitting accuracy. The right one shows the landmarks overlayed on the 3D face model. The blue/red ones indicate visible/invisible landmarks. 1
2 Figure 2. The 300W-3D database. For each sample, the left one is the original image, the right one is the fitted 3DMM. 2. Database W-3D This database contains the images in 300W [4] and their ground truth 3D faces. It is constructed by fitting the 3D Morphable Model with the Multi-Features Framework [3]. Different from the original algorithm, the 3D landmarks are adjusted by landmark marching [5] and the 68-landmarks constraint is adopted throughout the fitting process. Each sample is checked, few failed samples are adjusted manually. Fig. 2 demonstrates some samples in the database W-LP The 300W across Large Poses (300W-LP) database contains the synthesized face images from the face profiling algorithm described in Section 4. Some samples are demonstrated in Fig. 4. Besides, Fig. 3(a) and Fig. 3(b) demonstrate the yaw angle distribution before and after face profiling respectively. The distribution is reversed since face profiling only enlarges the yaw angle without shrinking it. Considering that the fidelity of a synthesized sample is negatively related with the yaw, we augment each training sample with the times of d(5 0.8 yaw/5 )e. Fig. 3(c) shows the yaw distribution after augmentation. (a) (b) (c) Figure 3. The yaw angle distribution of (a) 300W, (b) 300W-LP, (c) After augmentation AFLW2000-3D The AFLW2000-3D database contains the first 2000 samples in AFLW [2] with their ground truth 3D faces. This database is more challenging to construct than 300W-3D because the AFLW ignores the occluded landmarks (both occluded and self-
3 Figure 4. The 300W-LP database. For each sample, the first is the original image, followed by synthesized larger-pose faces, each with increased 10 degree yaw. Figure 5. The AFLW2000-3D database. For each sample, the left one is the original image, the right one is the fitted 3DMM. occluded) and the landmarks do not contain expression information (without lip landmarks). As a result we need a specifical method to deal with the unstandardised landmarks. Firstly, since AFLW provides the ground truth pose information, we
4 train a pose-dependent SDM (a SDM model for each yaw interval) with 68-landmark makeup on 300W-LP, with which the AFLW2000 is coarsely aligned for initialization. Secondly, we run Multi-Features Framework (MFF) 3DMM fitting method initialized by the 68 landmarks and constrained by the provided 21 visible landmarks. Finally, for the failed results, we label the necessary landmarks (always the upper and lower lip landmarks) and re-run the MFF. Fig. 5 demonstrates some samples in AFLW2000-3D. 3. Derivative of Vertex Distance Cost (VDC) The Vertex Distance Cost is defined in Section 3.4.2: E vdc = V (p 0 + p) V (p g ) 2 (1) where p = [f, pit, yaw, rol, t 2d, α id, α exp ] T contains all the parameters including the scale f, rotation angles pit, yaw, rol (which are short for pitch,yaw,roll), translation t 2d, shape α id and expression α exp. V (p) is the model construction and projection process defined as: V (p) = f Pr R (S + A id α id + A exp α exp ) + t 2d (2) [ ] Pr = R = R pit R yaw R rol (3) cos(yaw) 0 sin(yaw) cos(rol) sin(rol) 0 R pit = 0 cos(pit) sin(pit) R yaw = R rol = sin(rol) cos(rol) 0 (4) 0 sin(pit) cos(pit) sin(yaw) 0 cos(yaw) where S is the mean 3D shape, A id and A exp are the shape and expression PCA models respectively and Pr is the weak perspective projection matrix. The derivative of VDC is [ p = f pit E vdc p = (V (p0 + p) V (p g )) T p yaw rol t 2dx p=p0 + p t 2dy α id ] (:) α exp (5) (6) R pit = f = Pr R (S + A idα id + A exp α exp ) (7) pit = f Pr R pit R yaw R rol (S + A id α id + A exp α exp ) (8) yaw = f Pr R pit R yaw R rol (S + A id α id + A exp α exp ) (9) rol = f Pr R pit R yaw R rol (S + A id α id + A exp α exp ) (10) [ ] [ ] = = (11) t 2dx t 2dy = f Pr R A id = f Pr R A exp α id α exp (12) sin(pit) cos(pit) R yaw = 0 cos(pit) sin(pit) where (:) is the concatenation operator which is the same as Matlab. sin(yaw) 0 cos(yaw) sin(rol) cos(rol) R rol = cos(rol) sin(rol) 0, cos(yaw) 0 sin(yaw) (13)
5 References [1] T. Hassner, S. Harel, E. Paz, and R. Enbar. Effective face frontalization in unconstrained images. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June [2] M. Köstinger, P. Wohlhart, P. M. Roth, and H. Bischof. Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization. In Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on, pages IEEE, [3] S. Romdhani and T. Vetter. Estimating 3D shape and texture using pixel intensity, edges, specular highlights, texture constraints and a prior. In Computer Vision and Pattern Recognition (CVPR), 2005 IEEE Conference on, volume 2, pages IEEE, [4] C. Sagonas, G. Tzimiropoulos, S. Zafeiriou, and M. Pantic. 300 faces in-the-wild challenge: The first facial landmark localization challenge. In Computer Vision Workshops (ICCVW), 2013 IEEE International Conference on, pages IEEE, [5] X. Zhu, Z. Lei, J. Yan, D. Yi, and S. Z. Li. High-fidelity pose and expression normalization for face recognition in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages ,
Face Alignment Across Large Poses: A 3D Solution
Face Alignment Across Large Poses: A 3D Solution Outline Face Alignment Related Works 3D Morphable Model Projected Normalized Coordinate Code Network Structure 3D Image Rotation Performance on Datasets
More informationSupplementary Material for Synthesizing Normalized Faces from Facial Identity Features
Supplementary Material for Synthesizing Normalized Faces from Facial Identity Features Forrester Cole 1 David Belanger 1,2 Dilip Krishnan 1 Aaron Sarna 1 Inbar Mosseri 1 William T. Freeman 1,3 1 Google,
More informationLandmark Weighting for 3DMM Shape Fitting
Landmark Weighting for 3DMM Shape Fitting Yu Yang a, Xiao-Jun Wu a, and Josef Kittler b a School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China b CVSSP, University of Surrey,
More informationFace Recognition Markus Storer, 2007
Face Recognition Markus Storer, 2007 Agenda Face recognition by humans 3D morphable models pose and illumination model creation model fitting results Face recognition vendor test 2006 Face Recognition
More informationMoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction
MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction Ayush Tewari Michael Zollhofer Hyeongwoo Kim Pablo Garrido Florian Bernard Patrick Perez Christian Theobalt
More informationDeep Face Feature for Face Alignment and Reconstruction
1 Deep Face Feature for Face Alignment and Reconstruction Boyi Jiang, Juyong Zhang, Bailin Deng, Yudong Guo and Ligang Liu arxiv:1708.02721v1 [cs.cv] 9 Aug 2017 Abstract In this paper, we propose a novel
More informationRobust FEC-CNN: A High Accuracy Facial Landmark Detection System
Robust FEC-CNN: A High Accuracy Facial Landmark Detection System Zhenliang He 1,2 Jie Zhang 1,2 Meina Kan 1,3 Shiguang Shan 1,3 Xilin Chen 1 1 Key Lab of Intelligent Information Processing of Chinese Academy
More informationLocating Facial Landmarks Using Probabilistic Random Forest
2324 IEEE SIGNAL PROCESSING LETTERS, VOL. 22, NO. 12, DECEMBER 2015 Locating Facial Landmarks Using Probabilistic Random Forest Changwei Luo, Zengfu Wang, Shaobiao Wang, Juyong Zhang, and Jun Yu Abstract
More informationSupplementary Materials for A Lighting Robust Fitting Approach of 3D Morphable Model For Face Reconstruction
Noname manuscript No. (will be inserted by the editor) Supplementary Materials for A Lighting Robust Fitting Approach of 3D Morphable Model For Face Reconstruction Mingyang Ma Silong Peng Xiyuan Hu Received:
More informationarxiv: v2 [cs.cv] 8 Sep 2017
Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression Aaron S. Jackson 1 Adrian Bulat 1 Vasileios Argyriou 2 Georgios Tzimiropoulos 1 1 The University of Nottingham,
More informationA Fully End-to-End Cascaded CNN for Facial Landmark Detection
2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition A Fully End-to-End Cascaded CNN for Facial Landmark Detection Zhenliang He 1,2 Meina Kan 1,3 Jie Zhang 1,2 Xilin Chen 1 Shiguang
More informationFace Alignment across Large Pose via MT-CNN based 3D Shape Reconstruction
Face Alignment across Large Pose via MT-CNN based 3D Shape Reconstruction Gang Zhang 1,2, Hu Han 1, Shiguang Shan 1,2,3, Xingguang Song 4, Xilin Chen 1,2 1 Key Laboratory of Intelligent Information Processing
More informationPose-Invariant Face Alignment with a Single CNN
Pose-Invariant Face Alignment with a Single CNN Amin Jourabloo 1, Mao Ye 2, Xiaoming Liu 1, and Liu Ren 2 1 Department of Computer Science and Engineering, Michigan State University, MI 2 Bosch Research
More informationarxiv: v1 [cs.cv] 11 Jun 2015
Pose-Invariant 3D Face Alignment Amin Jourabloo, Xiaoming Liu Department of Computer Science and Engineering Michigan State University, East Lansing MI 48824 {jourablo, liuxm}@msu.edu arxiv:506.03799v
More informationIntensity-Depth Face Alignment Using Cascade Shape Regression
Intensity-Depth Face Alignment Using Cascade Shape Regression Yang Cao 1 and Bao-Liang Lu 1,2 1 Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai
More informationFaster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses
Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses Chandrasekhar Bhagavatula, Chenchen Zhu, Khoa Luu, and Marios Savvides Carnegie Mellon University
More informationSelf-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material
Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material Ayush Tewari 1,2 Michael Zollhöfer 1,2,3 Pablo Garrido 1,2 Florian Bernard 1,2 Hyeongwoo
More informationThe Nottingham eprints service makes this work by researchers of the University of Nottingham available open access under the following conditions.
Sagonas, Christos and Tzimiropoulos, Georgios and Zafeiriou, Stefanos and Pantic, Maja (2013) 300 Faces in-the-wild Challenge: the first facial landmark localization challenge. In: 2013 IEEE International
More informationPix2Face: Direct 3D Face Model Estimation
Pix2Face: Direct 3D Face Model Estimation Daniel Crispell Maxim Bazik Vision Systems, Inc Providence, RI USA danielcrispell, maximbazik@visionsystemsinccom Abstract An efficient, fully automatic method
More informationarxiv: v1 [cs.cv] 29 Sep 2016
arxiv:1609.09545v1 [cs.cv] 29 Sep 2016 Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge Adrian Bulat and Georgios Tzimiropoulos Computer Vision
More informationShape Augmented Regression for 3D Face Alignment
Shape Augmented Regression for 3D Face Alignment Chao Gou 1,3(B),YueWu 2, Fei-Yue Wang 1,3, and Qiang Ji 2 1 Institute of Automation, Chinese Academy of Sciences, Beijing, China {gouchao2012,feiyue.wang}@ia.ac.cn
More informationFacial Landmark Tracking by Tree-based Deformable Part Model Based Detector
Facial Landmark Tracking by Tree-based Deformable Part Model Based Detector Michal Uřičář, Vojtěch Franc, and Václav Hlaváč Department of Cybernetics, Faculty Electrical Engineering Czech Technical University
More information3D Active Appearance Model for Aligning Faces in 2D Images
3D Active Appearance Model for Aligning Faces in 2D Images Chun-Wei Chen and Chieh-Chih Wang Abstract Perceiving human faces is one of the most important functions for human robot interaction. The active
More informationMotion capturing via computer vision and machine learning
Motion capturing via computer vision and machine learning A live demonstration & talk Justin Tennant June 13, 2017 San Jose State University What is Stringless? Facial motion capture ( expression tracking
More information3D Face Modelling Under Unconstrained Pose & Illumination
David Bryan Ottawa-Carleton Institute for Biomedical Engineering Department of Systems and Computer Engineering Carleton University January 12, 2009 Agenda Problem Overview 3D Morphable Model Fitting Model
More informationarxiv: v1 [cs.cv] 16 Nov 2015
Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression Zhiao Huang hza@megvii.com Erjin Zhou zej@megvii.com Zhimin Cao czm@megvii.com arxiv:1511.04901v1 [cs.cv] 16 Nov 2015 Abstract Facial
More informationarxiv: v1 [cs.cv] 24 Sep 2018
MobileFace: 3D Face Reconstruction with Efficient CNN Regression Nikolai Chinaev 1, Alexander Chigorin 1, and Ivan Laptev 1,2 arxiv:1809.08809v1 [cs.cv] 24 Sep 2018 1 VisionLabs, Amsterdam, The Netherlands
More informationHuman Face Shape Analysis under Spherical Harmonics Illumination Considering Self Occlusion
Human Face Shape Analysis under Spherical Harmonics Illumination Considering Self Occlusion Jasenko Zivanov Andreas Forster Sandro Schönborn Thomas Vetter jasenko.zivanov@unibas.ch forster.andreas@gmail.com
More informationEvaluation of Dense 3D Reconstruction from 2D Face Images in the Wild
Evaluation of Dense 3D Reconstruction from 2D Face Images in the Wild Zhen-Hua Feng 1 Patrik Huber 1 Josef Kittler 1 Peter Hancock 2 Xiao-Jun Wu 3 Qijun Zhao 4 Paul Koppen 1 Matthias Rätsch 5 1 Centre
More informationOn 3D face reconstruction via cascaded regression in shape space
1978 Liu et al. / Front Inform Technol Electron Eng 2017 18(12):1978-1990 Frontiers of Information Technology & Electronic Engineering www.jzus.zju.edu.cn; engineering.cae.cn; www.springerlink.com ISSN
More informationOVer the last few years, cascaded-regression (CR) based
1 Random Cascaded-Regression Copse for Robust Facial Landmark Detection Zhen-Hua Feng 1,2, Student Member, IEEE, Patrik Huber 2, Josef Kittler 2, Life Member, IEEE, William Christmas 2, and Xiao-Jun Wu
More informationFace Alignment Under Various Poses and Expressions
Face Alignment Under Various Poses and Expressions Shengjun Xin and Haizhou Ai Computer Science and Technology Department, Tsinghua University, Beijing 100084, China ahz@mail.tsinghua.edu.cn Abstract.
More informationCombining Local and Global Features for 3D Face Tracking
Combining Local and Global Features for 3D Face Tracking Pengfei Xiong, Guoqing Li, Yuhang Sun Megvii (face++) Research {xiongpengfei, liguoqing, sunyuhang}@megvii.com Abstract In this paper, we propose
More informationHow far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks) Adrian Bulat and Georgios Tzimiropoulos Computer Vision Laboratory, The University of Nottingham
More informationTowards Large-Pose Face Frontalization in the Wild
Towards Large-Pose Face Frontalization in the Wild Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu and Manmohan Chandraker Michigan State University University of California, San Diego NEC Laboratories America
More informationarxiv:submit/ [cs.cv] 7 Sep 2017
How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks) arxiv:submit/2000193 [cs.cv] 7 Sep 2017 Adrian Bulat and Georgios Tzimiropoulos Computer Vision
More informationImproved Face Detection and Alignment using Cascade Deep Convolutional Network
Improved Face Detection and Alignment using Cascade Deep Convolutional Network Weilin Cong, Sanyuan Zhao, Hui Tian, and Jianbing Shen Beijing Key Laboratory of Intelligent Information Technology, School
More informationarxiv: v3 [cs.cv] 26 Aug 2018 Abstract
Nonlinear 3D Face Morphable Model Luan Tran, Xiaoming Liu Department of Computer Science and Engineering Michigan State University, East Lansing MI 48824 {tranluan, liuxm}@msu.edu arxiv:1804.03786v3 [cs.cv]
More informationPose-Invariant Face Alignment via CNN-Based Dense 3D Model Fitting
DOI 10.1007/s11263-017-1012-z Pose-Invariant Face Alignment via CNN-Based Dense 3D Model Fitting Amin Jourabloo 1 Xiaoming Liu 1 Received: 12 June 2016 / Accepted: 6 April 2017 Springer Science+Business
More informationDisentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition
Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition Feng Liu 1, Ronghang Zhu 1,DanZeng 1, Qijun Zhao 1,, and Xiaoming Liu 2 1 College of Computer Science, Sichuan University
More informationarxiv: v1 [cs.cv] 21 Mar 2018
arxiv:1803.07835v1 [cs.cv] 21 Mar 2018 Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network Yao Feng, Fan Wu, Xiaohu Shao, Yanfeng Wang, Xi Zhou Shanghai Jiao Tong University,
More informationJoint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network Yao Feng 1[0000 0002 9481 9783], Fan Wu 2[0000 0003 1970 3470], Xiaohu Shao 3,4[0000 0003 1141 6020], Yanfeng Wang
More informationarxiv: v1 [cs.cv] 17 Aug 2017
Robust Registration and Geometry Estimation from Unstructured Facial Scans arxiv:1708.05340v1 [cs.cv] 17 Aug 2017 Maxim Bazik1 and Daniel Crispell2 Abstract Commercial off the shelf (COTS) 3D scanners
More information3D Morphable Model Parameter Estimation
3D Morphable Model Parameter Estimation Nathan Faggian 1, Andrew P. Paplinski 1, and Jamie Sherrah 2 1 Monash University, Australia, Faculty of Information Technology, Clayton 2 Clarity Visual Intelligence,
More informationarxiv: v5 [cs.cv] 26 Jul 2017
arxiv:6.8657v5 [cs.cv] 26 Jul 27 Convolutional Experts Network for Facial Landmark Detection Amir Zadeh Carnegie Mellon University 5 Forbes Ave, Pittsburgh, PA 523, USA Tadas Baltrus aitis Carnegie Mellon
More informationUnconstrained Face Alignment without Face Detection
Unconstrained Face Alignment without Face Detection Xiaohu Shao 1,2, Junliang Xing 3, Jiangjing Lv 1,2, Chunlin Xiao 4, Pengcheng Liu 1, Youji Feng 1, Cheng Cheng 1 1 Chongqing Institute of Green and Intelligent
More informationJoint Head Pose Estimation and Face Alignment Framework Using Global and Local CNN Features
2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition Joint Head Pose Estimation and Face Alignment Framework Using Global and Local CNN Features Xiang Xu and Ioannis A. Kakadiaris
More informationLearn to Combine Multiple Hypotheses for Accurate Face Alignment
2013 IEEE International Conference on Computer Vision Workshops Learn to Combine Multiple Hypotheses for Accurate Face Alignment Junjie Yan Zhen Lei Dong Yi Stan Z. Li Center for Biometrics and Security
More informationIn Between 3D Active Appearance Models and 3D Morphable Models
In Between 3D Active Appearance Models and 3D Morphable Models Jingu Heo and Marios Savvides Biometrics Lab, CyLab Carnegie Mellon University Pittsburgh, PA 15213 jheo@cmu.edu, msavvid@ri.cmu.edu Abstract
More informationTweaked residual convolutional network for face alignment
Journal of Physics: Conference Series PAPER OPEN ACCESS Tweaked residual convolutional network for face alignment To cite this article: Wenchao Du et al 2017 J. Phys.: Conf. Ser. 887 012077 Related content
More informationSimultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion
Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion Yue Wu Chao Gou Qiang Ji ECSE Department Institute of Automation ECSE Department Rensselaer Polytechnic Institute
More informationReflective Regression of 2D-3D Face Shape Across Large Pose
JIA, YANG, ZHU, KUANG, NIU, CHAN: RCCR FOR LARGE POSE 1 Reflective Regression of 2D-3D Face Shape Across Large Pose Xuhui Jia 1 xhjia@cs.hku.hk Heng Yang 2 yanghengnudt@gmail.com Xiaolong Zhu 3 lucienzhu@gmail.com
More informationNonrigid Surface Modelling. and Fast Recovery. Department of Computer Science and Engineering. Committee: Prof. Leo J. Jia and Prof. K. H.
Nonrigid Surface Modelling and Fast Recovery Zhu Jianke Supervisor: Prof. Michael R. Lyu Committee: Prof. Leo J. Jia and Prof. K. H. Wong Department of Computer Science and Engineering May 11, 2007 1 2
More informationCascade Multi-view Hourglass Model for Robust 3D Face Alignment
Cascade Multi-view Hourglass Model for Robust 3D Face Alignment Jiankang Deng 1, Yuxiang Zhou 1, Shiyang Cheng 1, and Stefanos Zaferiou 1,2 1 Department of Computing, Imperial College London, UK 2 Centre
More informationDeep Alignment Network: A convolutional neural network for robust face alignment
Deep Alignment Network: A convolutional neural network for robust face alignment Marek Kowalski, Jacek Naruniec, and Tomasz Trzcinski Warsaw University of Technology m.kowalski@ire.pw.edu.pl, j.naruniec@ire.pw.edu.pl,
More informationDataset Augmentation for Pose and Lighting Invariant Face Recognition
Dataset Augmentation for Pose and Lighting Invariant Face Recognition Daniel Crispell, Octavian Biris, Nate Crosswhite, Jeffrey Byrne, Joseph L. Mundy Vision Systems, Inc. Systems and Technology Research
More informationHolistically Constrained Local Model: Going Beyond Frontal Poses for Facial Landmark Detection
KIM, BALTRUŠAITIS et al.: HOLISTICALLY CONSTRAINED LOCAL MODEL 1 Holistically Constrained Local Model: Going Beyond Frontal Poses for Facial Landmark Detection KangGeon Kim 1 kanggeon.kim@usc.edu Tadas
More informationarxiv: v2 [cs.cv] 4 Mar 2018
Load Balanced GANs for Multi-view Face Image Synthesis Jie Cao 1,2,4, Yibo Hu 1,2,4, Bing Yu 5, Ran He 1,2,3,4 and Zhenan Sun 1,2,3,4 1 National Laboratory of Pattern Recognition, CASIA 2 Center for Research
More informationSparse Shape Registration for Occluded Facial Feature Localization
Shape Registration for Occluded Facial Feature Localization Fei Yang, Junzhou Huang and Dimitris Metaxas Abstract This paper proposes a sparsity driven shape registration method for occluded facial feature
More informationDeep Evolutionary 3D Diffusion Heat Maps for Large-pose Face Alignment
SUN, SHAO, XIA, FU: DEEP EVOLUTIONARY 3D DHM FOR FACE ALIGNMENT 1 Deep Evolutionary 3D Diffusion Heat Maps for Large-pose Face Alignment Bin Sun 1 sun.bi@husky.neu.edu Ming Shao 2 mshao@umassd.edu Siyu
More informationRapid 3D Face Modeling using a Frontal Face and a Profile Face for Accurate 2D Pose Synthesis
Rapid 3D Face Modeling using a Frontal Face and a Profile Face for Accurate 2D Pose Synthesis Jingu Heo and Marios Savvides CyLab Biometrics Center Carnegie Mellon University Pittsburgh, PA 15213 jheo@cmu.edu,
More informationReal-time Multi-view Facial Landmark Detector Learned by the Structured Output SVM
Real-time Multi-view Facial Landmark Detector Learned by the Structured Output SVM Michal Ur ic a r 1, Vojte ch Franc1, Diego Thomas2, Akihiro Sugimoto2, and Va clav Hlava c 1 1 Center for Machine Perception,
More informationarxiv: v1 [cs.cv] 2 Sep 2017
Facial 3D Model Registration Under Occlusions With SensiblePoints-based Reinforced Hypothesis Refinement arxiv:1709.00531v1 [cs.cv] 2 Sep 2017 Yuhang Wu and Ioannis A. Kakadiaris Computational Biomedicine
More informationEnhanced Active Shape Models with Global Texture Constraints for Image Analysis
Enhanced Active Shape Models with Global Texture Constraints for Image Analysis Shiguang Shan, Wen Gao, Wei Wang, Debin Zhao, Baocai Yin Institute of Computing Technology, Chinese Academy of Sciences,
More informationSingle view-based 3D face reconstruction robust to self-occlusion
Lee et al. EURASIP Journal on Advances in Signal Processing 2012, 2012:176 RESEARCH Open Access Single view-based 3D face reconstruction robust to self-occlusion Youn Joo Lee 1, Sung Joo Lee 2, Kang Ryoung
More informationGeneric Face Alignment Using an Improved Active Shape Model
Generic Face Alignment Using an Improved Active Shape Model Liting Wang, Xiaoqing Ding, Chi Fang Electronic Engineering Department, Tsinghua University, Beijing, China {wanglt, dxq, fangchi} @ocrserv.ee.tsinghua.edu.cn
More informationLandmark Detection and 3D Face Reconstruction using Modern C++
Landmark Detection and 3D Face Reconstruction using Modern C++ Patrik Huber Centre for Vision, Speech and Signal Processing University of Surrey, UK p.huber@surrey.ac.uk BMVA technical meeting: The Computational
More informationDynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting
Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting Zhen-Hua Feng 1 Josef Kittler 1 William Christmas 1 Patrik Huber 1 Xiao-Jun Wu
More informationSieving Regression Forest Votes for Facial Feature Detection in the Wild
23 IEEE International Conference on Computer Vision Sieving Regression Forest Votes for Facial Feature Detection in the Wild Heng Yang and Ioannis Patras Queen Mary University of London {heng.yang, i.patras}@eecs.qmul.ac.uk
More informationarxiv: v2 [cs.cv] 10 Aug 2017
Deep Alignment Network: A convolutional neural network for robust face alignment Marek Kowalski, Jacek Naruniec, and Tomasz Trzcinski arxiv:1706.01789v2 [cs.cv] 10 Aug 2017 Warsaw University of Technology
More informationAnalyzing the Relationship Between Head Pose and Gaze to Model Driver Visual Attention
Analyzing the Relationship Between Head Pose and Gaze to Model Driver Visual Attention Sumit Jha and Carlos Busso Multimodal Signal Processing (MSP) Laboratory Department of Electrical Engineering, The
More informationAbstract We present a system which automatically generates a 3D face model from a single frontal image of a face. Our system consists of two component
A Fully Automatic System To Model Faces From a Single Image Zicheng Liu Microsoft Research August 2003 Technical Report MSR-TR-2003-55 Microsoft Research Microsoft Corporation One Microsoft Way Redmond,
More informationFace Recognition Using a Unified 3D Morphable Model
Face Recognition Using a Unified 3D Morphable Model Hu, G., Yan, F., Chan, C-H., Deng, W., Christmas, W., Kittler, J., & Robertson, N. M. (2016). Face Recognition Using a Unified 3D Morphable Model. In
More informationConvolutional Experts Constrained Local Model for 3D Facial Landmark Detection
Correction Network FC200 FC200 Final Prediction Convolutional Experts Constrained Local Model for 3D Facial Landmark Detection Amir Zadeh, Yao Chong Lim, Tadas Baltrušaitis, Louis-Philippe Morency Carnegie
More informationLearning Detailed Face Reconstruction from a Single Image
Learning Detailed Face Reconstruction from a Single Image Elad Richardson 1 Matan Sela 1 Roy Or-El 2 Ron Kimmel 1 1 Department of Computer Science, Technion - Israel Institute of Technology 2 Department
More informationFace View Synthesis Across Large Angles
Face View Synthesis Across Large Angles Jiang Ni and Henry Schneiderman Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 1513, USA Abstract. Pose variations, especially large out-of-plane
More informationFace Detection by Aggregating Visible Components
Face Detection by Aggregating Visible Components Jiali Duan 1, Shengcai Liao 2, Xiaoyuan Guo 3, and Stan Z. Li 2 1 School of Electronic, Electrical and Communication Engineering University of Chinese Academy
More informationPartial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge
Partial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge Dong Yi, Shengcai Liao, Zhen Lei, Jitao Sang, and Stan Z. Li Center for Biometrics and Security Research, Institute
More informationCoarse-to-Fine Statistical Shape Model by Bayesian Inference
Coarse-to-Fine Statistical Shape Model by Bayesian Inference Ran He, Stan Li, Zhen Lei and ShengCai Liao Institute of Automation, Chinese Academy of Sciences, Beijing, China. {rhe@nlpr.ia.ac.cn} Abstract.
More informationThe First 3D Face Alignment in the Wild (3DFAW) Challenge
The First 3D Face Alignment in the Wild (3DFAW) Challenge László A. Jeni 1, Sergey Tulyakov 2, Lijun Yin 3, Nicu Sebe 2, and Jeffrey F. Cohn 1,4 1 Robotics Institute, Carnegie Mellon University, Pittsburgh,
More informationFace Detection and Tracking Control with Omni Car
Face Detection and Tracking Control with Omni Car Jheng-Hao Chen, Tung-Yu Wu CS 231A Final Report June 31, 2016 Abstract We present a combination of frontal and side face detection approach, using deep
More informationSUPPLEMENTARY MATERIAL FOR: ADAPTIVE CASCADED REGRESSION
SUPPLEMENTARY MATERIAL FOR: ADAPTIVE CASCADED REGRESSION Epameinondas Antonakos,, Patrick Snape,, George Trigeorgis, Stefanos Zafeiriou, Department of Computing, Imperial College London, U.K. Center for
More informationFace Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild
Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild Zhen-Hua Feng 1,2 Josef Kittler 1 Muhammad Awais 1 Patrik Huber 1 Xiao-Jun Wu 2 1 Centre
More informationWing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks Zhen-Hua Feng 1 Josef Kittler 1 Muhammad Awais 1 Patrik Huber 1 Xiao-Jun Wu 2 1 Centre for Vision, Speech and Signal
More informationFitting a Single Active Appearance Model Simultaneously to Multiple Images
Fitting a Single Active Appearance Model Simultaneously to Multiple Images Changbo Hu, Jing Xiao, Iain Matthews, Simon Baker, Jeff Cohn, and Takeo Kanade The Robotics Institute, Carnegie Mellon University
More informationA Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection
A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection Jiangjing Lv 1,2, Xiaohu Shao 1,2, Junliang Xing 3, Cheng Cheng 1, Xi Zhou 1 1 Chongqing Institute
More informationCross-pose Facial Expression Recognition
Cross-pose Facial Expression Recognition Abstract In real world facial expression recognition (FER) applications, it is not practical for a user to enroll his/her facial expressions under different pose
More informationMULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS. Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo
MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS Yanghao Li, Jiaying Liu, Wenhan Yang, Zongg Guo Institute of Computer Science and Technology, Peking University, Beijing, P.R.China,
More informationFace Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild
Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild Zhen-Hua Feng 1,2 Josef Kittler 1 Muhammad Awais 1 Patrik Huber 1 Xiao-Jun Wu 2 1 Centre
More informationFace Detection Algorithm Based on a Cascade of Ensembles of Decision Trees
454 Lebedev A., Khryashchev V., Priorov A. Face Detection Algorithm Based on a Cascade of Ensembles of Decision Trees Anton Lebedev, Vladimir Pavlov, Vladimir Khryashchev, Olga Stepanova P.G. Demidov Yaroslavl
More informationFacial shape tracking via spatio-temporal cascade shape regression
Facial shape tracking via spatio-temporal cascade shape regression Jing Yang nuist yj@126.com Jiankang Deng jiankangdeng@gmail.com Qingshan Liu Kaihua Zhang zhkhua@gmail.com qsliu@nuist.edu.cn Nanjing
More informationTEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA
TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA Tomoki Hayashi 1, Francois de Sorbier 1 and Hideo Saito 1 1 Graduate School of Science and Technology, Keio University, 3-14-1 Hiyoshi,
More informationHigh-Fidelity Pose and Expression Normalization for Face Recognition in the Wild
High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild Xiangyu Zhu Zhen Lei Junjie Yan Dong Yi Stan Z. Li Center for Biometrics and Security Research & National Laboratory of
More informationFacial Feature Points Tracking Based on AAM with Optical Flow Constrained Initialization
Journal of Pattern Recognition Research 7 (2012) 72-79 Received Oct 24, 2011. Revised Jan 16, 2012. Accepted Mar 2, 2012. Facial Feature Points Tracking Based on AAM with Optical Flow Constrained Initialization
More informationOcclusion Robust Multi-Camera Face Tracking
Occlusion Robust Multi-Camera Face Tracking Josh Harguess, Changbo Hu, J. K. Aggarwal Computer & Vision Research Center / Department of ECE The University of Texas at Austin harguess@utexas.edu, changbo.hu@gmail.com,
More informationCollaborative Facial Landmark Localization for Transferring Annotations Across Datasets
Collaborative Facial Landmark Localization for Transferring Annotations Across Datasets Brandon M. Smith and Li Zhang University of Wisconsin Madison http://www.cs.wisc.edu/~lizhang/projects/collab-face-landmarks/
More informationDe-mark GAN: Removing Dense Watermark With Generative Adversarial Network
De-mark GAN: Removing Dense Watermark With Generative Adversarial Network Jinlin Wu, Hailin Shi, Shu Zhang, Zhen Lei, Yang Yang, Stan Z. Li Center for Biometrics and Security Research & National Laboratory
More informationFace Recognition Based on Pose-Variant Image Synthesis and Multi-level Multi-feature Fusion
Face Recognition Based on Pose-Variant Image Synthesis and Multi-level Multi-feature Fusion Congcong Li, Guangda Su, Yan Shang, Yingchun Li, and Yan Xiang Electronic Engineering Department, Tsinghua University,
More informationarxiv: v5 [cs.cv] 13 Apr 2018
Fine-Grained Head Pose Estimation Without Keypoints Nataniel Ruiz Eunji Chong James M. Rehg Georgia Institute of Technology {nataniel.ruiz, eunjichong, rehg}@gatech.edu arxiv:1710.00925v5 [cs.cv] 13 Apr
More informationGeneric Active Appearance Models Revisited
Generic Active Appearance Models Revisited Georgios Tzimiropoulos 1,2, Joan Alabort-i-Medina 1, Stefanos Zafeiriou 1, and Maja Pantic 1,3 1 Department of Computing, Imperial College London, United Kingdom
More information